CN103366555B - Aerial image-based traffic accident scene image rapid generation method and system - Google Patents
Aerial image-based traffic accident scene image rapid generation method and system Download PDFInfo
- Publication number
- CN103366555B CN103366555B CN201310272101.XA CN201310272101A CN103366555B CN 103366555 B CN103366555 B CN 103366555B CN 201310272101 A CN201310272101 A CN 201310272101A CN 103366555 B CN103366555 B CN 103366555B
- Authority
- CN
- China
- Prior art keywords
- image
- scene
- coordinate
- camera
- display module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses an aerial image-based traffic accident scene image rapid generation method and an aerial image-based traffic accident scene image rapid generation system. The scene image generation method comprises the following steps: shooting an accident scene image by utilizing an aerial platform and generating an orthographic image; displaying a realistic image serving as a background image on a display module, generating a vehicle image and a road edge image by using a template generation module; generating an environmental object image, a scattered object image, a shallow road surface scratch image and a braking trace image by using the template generation module; measuring the distance among traffic elements and marking on the display module by using a distance marking module; marking other information required by a standard scene image on the display module; and deleting the background image from the display module, and generating and displaying an affiliated area by using an affiliated region generation module. By the aerial image-based traffic accident scene image rapid generation method disclosed by the invention, the standard traffic accident scene image can be generated rapidly and accurately by utilizing the aerial image without drawing by hands.
Description
Technical field
The present invention relates to scene of a traffic accident prospecting technique field, be specifically related to a kind of traffic accident scene diagram rapid generation based on Aerial Images and system.
Background technology
The drafting of scene of the accident exploration and scene photo is the first link of Traffic Accident Disposing.Main task comprises measurement and equal proportion drafting, the floor photo etc. of on-the-spot multiple key element.To in the shooting of the scene of a traffic accident, usual employing camera is taken, each photo shot can only reflect the accident conditions on a direction, reducing the scene of the accident needs to utilize situ measurements to carry out manual drawing schematic diagram on coordinate paper, and at present the scene of the accident is measured main dependence and is manually carried out, therefore there is following several respects limitation in manual drawing schematic diagram: (1) efficiency is extremely low, and the measurement drafting time is long, is unfavorable for the fast quick-recovery of the scene of a traffic accident; (2) manual measurement precision is lower, and manual drawing standard differs, the ratio of more difficult assurance car, road, vestige; (3) some key parameters are easily omitted, and cannot make up; (4) secondary checking cannot be carried out to accident scene.If in some disputable accident to part measurement size produce conflict between doubt or measurement size time, cannot secondary checking be carried out.
Summary of the invention
In order to overcome the defect existed in above-mentioned prior art, the object of this invention is to provide a kind of traffic accident scene diagram rapid generation based on Aerial Images and system, the present invention can utilize Aerial Images to generate the traffic accident scene diagram of standard rapidly and accurately.
In order to realize above-mentioned purpose of the present invention, according to a first aspect of the invention, the invention provides a kind of traffic accident scene diagram rapid generation based on Aerial Images, comprise the steps:
S1: utilize platform of taking photo by plane take scene of the accident image and generate the orthograph of outdoor scene;
S2: described orthograph is transferred to scene photo generating apparatus, described orthograph as a setting image shows at the display module of described scene photo generating apparatus, and the template generation module of described scene photo generating apparatus generates vehicle image and road edge image according to the vehicle of background image and road edge and the position that vehicle is corresponding with road edge described in display module shows;
S3: template generation module according to the environmental objects of background image, the object that is scattered, more shallow road surface scratch and braking track build environment subject image, fall-out volume image, more shallow road surface scratch image and braking track image and the position that environmental objects, the object that is scattered, more shallow road surface scratch and braking track are corresponding described in display module show;
S4: distance labeling module is measured the distance between traffic element and marks on display module;
S5: on display module, other information that standard field figure needs are marked;
S6: delete background image from display module, subzone generates template and generates on described display module and show subzone.
Traffic accident scene diagram rapid generation based on Aerial Images of the present invention does not need manual drawing, and Aerial Images can be utilized to generate the traffic accident scene diagram of standard rapidly and accurately.
In the preferred embodiment of the present invention, take photo by plane platform shooting scene of the accident image the method generating orthograph of described utilization comprises the steps:
S21: construct platform of taking photo by plane;
S22: shooting scene of the accident overhead view image;
S23: geometry correction is carried out to described overhead view image;
S24: carry out homogeneous coordinate transformation to described overhead view image, by the coordinate system transformation of described overhead view image to orthogonal projection coordinate system.
The method utilizing Aerial Images to generate orthogonal projection scene photo of the present invention can utilize the image of taking photo by plane to pass through geometry correction, homogeneous coordinate transformation obtains truly careful scene of the accident two dimensional image, full and accurate traffic accident scene diagram is generated again, efficiently and accurately reduction scene of the accident picture through image measurement, mark.Compared with prior art, measurement drafting time of the present invention short, ultrahigh in efficiency, is beneficial to the fast quick-recovery of the scene of a traffic accident; The present invention accurately can mark the position to car, road, vestige, and key parameter is preserved complete, and measuring accuracy is high, and the measuring error that human factor can be avoided to cause and gained scene photo arbitrarily can not be revised by subjectivity; In addition, the present invention can store the image of the scene of the accident, calls when needs, can carry out secondary checking to accident scene.
In another kind of preferred implementation of the present invention, the step of described geometry correction is:
S31: utilize two-dimensional calibrations plate to demarcate camera, construct image mapping equation, obtain inner parameter and the external parameter of camera, described inner parameter comprises distortion factor;
S32: the numerical value of distortion factor is adjusted to 0, keeps other parameter constant, obtains the inner parameter matrix of new camera;
S33: the inner parameter utilizing camera old substitutes into image mapped equation, solve the imaging plane coordinate that distorted image pixel coordinate is corresponding, recycle described new camera internal parameter and substitute into image mapped equation, bring imaging plane coordinate surface into new image mapped equation, obtain the image pixel coordinates after correcting, then realize color reduction by gray-level interpolation.
In the preferred embodiment of the present invention, the described two-dimensional calibrations plate that utilizes is demarcated camera, construct image mapping equation, and the step of the inner parameter and external parameter that obtain camera is:
S41: prepare two-dimensional calibrations plate, described two-dimensional calibrations plate has the pattern with certain area that at least 9, radiuses high with background contrasts and ranks spacing are fixed;
S42: utilize camera to be calibrated to take the image containing described scaling board of different angles;
S43: utilize image recognition algorithm search for the pattern in shooting image and locate and extract center-of-mass coordinate;
S44: utilize the two-dimentional actual coordinate of pattern and the described center-of-mass coordinate of extraction on scaling board to set up mapping equation, ask its optimum solution, obtain camera internal parameter and external parameter, described mapping equation is:
P
c＝RP
w+Τ；
Wherein, R is rotation matrix, and Τ is translation matrix, and described R, Τ are the external parameter of camera; P
wfor world coordinates, with (x
w, y
w, z
w) represent coordinate points in world coordinates, P
cfor it transforms to the coordinate in camera coordinates system, with (x
c, y
c, z
c) represent coordinate points in camera coordinates system; F is focal length, and u, v are desirable imaging plane coordinate; K is distortion factor, and u', v' are actual imaging planimetric coordinates; R is pixel line number, and c is pixel columns, S
x, S
yfor picture centre pixel coordinate, C
x, C
yfor the coordinate of principal point in imaging coordinate system.
The present invention can the distortion of correcting camera shooting image, obtains real scene of the accident picture, reduces scene of the accident picture efficiently and accurately.
In another kind of preferred implementation of the present invention, the homogeneous coordinate transformation equation adopted in step S24 is:
Wherein, a, b, c, d, e, f, u, v are coordinate transformation parameter, when calculating, choose 4 reference points and set up 8 equations, and each reference point all needing to have areal coordinate and corresponding two dimensional image coordinate two-dimensionally.
The present invention obtains truly careful scene of the accident two dimensional image by homogeneous coordinate transformation, then generates full and accurate traffic accident scene diagram through image labeling.
In another preferred implementation of the present invention, the template generation module of described scene photo generating apparatus generates vehicle image and road edge image according to the vehicle of background image and road edge.
The generation method of vehicle image is: generate car modal in the vehicle region of background image, vehicle edge search is carried out centered by car modal position, extract edge contour, and adopt rigid transformation to carry out registration to car modal according to the edge contour extracted;
The generation method of road edge image is: in the road edge Area generation road template of background image, described road template is straight line or curve, carry out Edge Search in road template both sides, extract edge contour, and road template is carried out to rigid transformation carry out registration according to the profile extracted.
In another kind of preferred implementation of the present invention, described distance labeling module measures the distance between traffic element and the method marked on display module is:
After traffic element is completed, in a segment distance known according to the scene of the accident and background image, full figure engineer's scale is set up in the contrast of respective distance, and distance labeling module is measured the distance between traffic element and generated to be labeled on display module and shows.
The present invention can generate vehicle image and road edge image according to the vehicle in background image and road edge, and marks the distance between traffic element, thus generates accident situ map quickly and accurately.
In order to realize above-mentioned purpose of the present invention, according to a second aspect of the invention, the invention provides a kind of traffic accident scene diagram quick-speed generation system based on Aerial Images, comprise take photo by plane platform and the scene photo generating apparatus that is connected with described platform of taking photo by plane, described scene photo generating apparatus comprises display module, template generation module, distance labeling module and subzone generation module; Described display module is connected with subzone generation module with described template generation module, distance labeling module respectively, described template generation module for generating the image of traffic element image and non-traffic element on described display module, described distance labeling module is for marking the distance between described traffic element, and described subzone generation module for generating subzone on display module.
Traffic accident scene diagram quick-speed generation system based on Aerial Images of the present invention does not need manual drawing, and Aerial Images can be utilized to generate the traffic accident scene diagram of standard rapidly and accurately.
In the preferred embodiment of the present invention, described platform of taking photo by plane comprises can go up to the air mobile device (2) and the camera (1) that carries thereof, described camera (1) shooting the scene of the accident (3) image and by described image transmitting to processor (4), described processor (4) method according to claim 1 utilizes Aerial Images to generate digitizing scene photo, obtains real accident scene.
Platform of taking photo by plane of the present invention can the distorted image of correcting camera machine shooting, obtains real scene of the accident picture, reduces scene of the accident picture efficiently and accurately.
In the preferred embodiment of the present invention, described camera passes through WiFi module by the image transmitting of the scene of the accident to processor.
Additional aspect of the present invention and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
Above-mentioned and/or additional aspect of the present invention and advantage will become obvious and easy understand from accompanying drawing below combining to the description of embodiment, wherein:
Fig. 1 is that the present invention utilizes Aerial Images to generate the structural representation of the system of orthogonal projection scene photo;
Fig. 2 is that a kind of preferred implementation Air China of the present invention claps the structural representation of platform;
Fig. 3 is that the present invention utilizes Aerial Images to generate the process flow diagram of the method for orthogonal projection scene photo.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Being exemplary below by the embodiment be described with reference to the drawings, only for explaining the present invention, and can not limitation of the present invention being interpreted as.
In describing the invention, unless otherwise prescribed and limit, it should be noted that, term " installation ", " being connected ", " connection " should be interpreted broadly, such as, can be mechanical connection or electrical connection, also can be the connection of two element internals, can be directly be connected, also indirectly can be connected by intermediary, for the ordinary skill in the art, the concrete meaning of above-mentioned term can be understood as the case may be.
The invention provides a kind of traffic accident scene diagram quick-speed generation system based on Aerial Images, as shown in Figure 1, comprise take photo by plane platform and the scene photo generating apparatus that is connected with described platform of taking photo by plane, described scene photo generating apparatus comprises display module, template generation module, distance labeling module and subzone generation module, described display module respectively with described template generation module, distance labeling module is connected with subzone generation module, described template generation module for generating the image of traffic element image and non-traffic element on described display module, in the present embodiment, traffic element refers to vehicle and road edge, non-traffic element refers to all elements except traffic element needed during scene photo is drawn, comprise environmental objects, be scattered object, more shallow road surface scratch and braking track etc., described distance labeling module is for marking the distance between described traffic element, described subzone generation module for generating subzone on display module.In the present embodiment, scene photo generating apparatus also comprises input media, manually can add the content that template generation module, distance labeling module and subzone generation module generate to viewing area by input media.In the preferred implementation that the present invention is other, it is outside that input media can be arranged at scene photo generating apparatus.
In the present embodiment, as shown in Figure 2, platform of taking photo by plane comprises can go up to the air mobile device 2 and the camera 1 that carries thereof, in present embodiment, can go up to the air mobile device 2 can for but be not limited to telecontrolled aircraft.The image of the scene of the accident 3 taken by camera 1 and by image transmitting to processor 4, processor, to correct image, obtains real accident scene.In the present embodiment, camera 1 passes through WiFi module by the image transmitting of the scene of the accident to processor 4, and processor 4 can process the image of camera shooting in real time.The same when needing image pickup method to take with camera with disposal route, the present invention does not repeat at this.
Present invention also offers a kind of traffic accident scene diagram rapid generation based on Aerial Images, before generation scene photo, need in template generation module, construct traffic accident situ map shape symbol guide, specifically according to National Standard of the People's Republic of China " traffic accident situ map pictograph number " (GB/T11797-2005), " traffic hazard files document " (GA40-2008), " traffic accident situ map drafting " (GA49-2009), " road signs and graticule " (GB5768-1999) draws vehicle, road, graticule, vestige, environmental objects, be scattered object, and the template of various curve and point.
As shown in Figure 3, the traffic accident scene diagram rapid generation based on Aerial Images comprises the steps:
S1: utilize and take photo by plane platform shooting scene of the accident image and generate orthograph;
S2: described realistic picture is transferred to scene photo generating apparatus, described realistic picture as a setting image shows at the display module of described scene photo generating apparatus, and the template generation module of described scene photo generating apparatus generates vehicle image and road edge image according to the vehicle of background image and road edge and the position that vehicle is corresponding with road edge described in display module shows;
S3: template generation module according to the environmental objects of background image, the object that is scattered, more shallow road surface scratch and braking track build environment subject image, fall-out volume image, more shallow road surface scratch image and braking track image and the position that environmental objects, the object that is scattered, more shallow road surface scratch and braking track are corresponding described in display module show;
S4: distance labeling module is measured the distance between traffic element and marks on display module;
S5: on display module, other information that standard field figure needs are marked;
S6: delete background image from display module, subzone generates template and generates on described display module and show subzone.
In the present embodiment, take photo by plane platform shooting scene of the accident image the method generating orthograph is utilized to comprise the steps:
S21: construct platform of taking photo by plane;
S22: shooting scene of the accident overhead view image;
S23: geometry correction is carried out to described overhead view image;
S24: carry out homogeneous coordinate transformation to described overhead view image, by the coordinate system transformation of described overhead view image to orthogonal projection coordinate system.
In the preferred embodiment of the present invention, utilize platform of taking photo by plane to take scene of the accident image and generate orthograph specifically to comprise the steps:
The first step: structure is taken photo by plane platform, in the present embodiment, platform of taking photo by plane for can steadily hovering can utilize GPS positioning flight, comprises can go up to the air mobile device 2 and the camera 1 that carries thereof.
Second step: shooting scene of the accident overhead view image, in the present embodiment, can by some fixed scenes of the scene of the accident, such as traffic sign, vehicles etc., as pattern identification plate, in the embodiment be more preferably of the present invention, can be provided with at least 4 pattern identification plates in the scene of the accident, the phase mutual edge distance of this pattern scaling board is known, for videographic measurment scale.In the present embodiment, in pattern identification plate, the shape of pattern is circular.In the present embodiment, the size of the phase mutual edge distance of pattern scaling board is relevant with the precision of homogeneous coordinate transformation, and the phase mutual edge distance of pattern scaling board is larger, and the precision of homogeneous coordinate transformation is higher, in the present embodiment, the neighbor distance of preferred pattern scaling board is 2 meters.The present invention utilizes pattern identification plate as coordinatometer, carries out homogeneous coordinate transformation, efficiently and accurately to the image of differing heights shooting.
3rd step: geometry correction is carried out to described overhead view image.In the present embodiment, camera adopts wide-angle lens, image radial distortion is comparatively serious, due to will image measurement be carried out, therefore geometry correction to be carried out to the image of distortion, utilize scaling board and calibrating procedure to demarcate aerial camera, and after utilizing the inherent parameter of renewal camera, image mapped equation carry out geometry correction to image.In the present embodiment, the step of geometry correction is:
S31: utilize two-dimensional calibrations plate to demarcate camera, construct image mapping equation, obtain inner parameter and the external parameter of camera, inner parameter comprises distortion factor.In the present embodiment, concrete steps are:
First, prepare two-dimensional calibrations plate, described two-dimensional calibrations plate has the pattern with certain area that at least 9, radiuses high with background contrasts and ranks spacing are fixed, in the preferred embodiment of the present invention, pattern comprises at least 9 circular diagrams separated from one another.
Then, utilizing camera to be calibrated to take the image containing described scaling board of different angles, when taking, ensureing bright and clear, shooting clear patterns.
Again, image recognition algorithm is utilized to search for the pattern in shooting image and locate and extract center-of-mass coordinate.
Finally, the two-dimentional actual coordinate of pattern and the described center-of-mass coordinate of extraction on scaling board is utilized to set up mapping equation, ask its optimum solution, in the present embodiment, least square method is utilized to solve mapping equation, obtain camera internal parameter and external parameter, in the present embodiment, inner parameter comprises focal length, distortion factor, principal point for camera coordinate, picture centre pixel coordinate, picture size in imaging coordinate system; External parameter comprises rotation matrix and the translation matrix of image, thus completes camera calibration, and in the preferred embodiment of the present invention, the mapping equation of employing is:
P
c＝RP
w+Τ；
Wherein, R is rotation matrix, and Τ is translation matrix, and described R, Τ are the external parameter of camera; P
wfor world coordinates, with (x
w, y
w, z
w) represent coordinate points in world coordinates, P
cfor it transforms to the coordinate in camera coordinates system, with (x
c, y
c, z
c) represent coordinate points in camera coordinates system; F is focal length, and u, v are desirable imaging plane coordinate; K is distortion factor, and u', v' are actual imaging planimetric coordinates; R is pixel line number, and c is pixel columns, S
x, S
yfor picture centre pixel coordinate, C
x, C
yfor the coordinate of principal point in imaging coordinate system.
S32: the numerical value of distortion factor is adjusted to 0, keeps other parameter constant, obtains the inner parameter matrix of new camera;
S33: the inner parameter utilizing camera old substitutes into image mapped equation, solve the imaging plane coordinate that distorted image pixel coordinate is corresponding, recycle described new camera internal parameter and substitute into image mapped equation, bring imaging plane coordinate surface into new image mapped equation, obtain the image pixel coordinates after correcting, then realize color reduction by gray-level interpolation.In the present embodiment, gray-level interpolation method can for but be not limited to nearest neighbor interpolation, namely to get around distortion pixel the gray scale of the nearest adjoint point pixel grey scale of four adjoint point pixel middle distances as this point.
The method utilizing Aerial Images to generate orthogonal projection scene photo of the present invention can the distortion of correcting camera shooting image, obtains real scene of the accident picture, reduces scene of the accident picture efficiently and accurately.
4th step: carry out homogeneous coordinate transformation to described overhead view image, by the coordinate system transformation of described overhead view image to orthogonal projection coordinate system.
In the present embodiment, utilize homogeneous coordinate transformation that the overhead view image of shooting is converted into orthogonal projection coordinate system, this orthogonal projection coordinate system and ground coordinate are translation relation, the image pixel dimensions of object and physical size direct proportionality on floor.In the present embodiment, the homogeneous coordinate transformation equation of employing is:
Wherein, a, b, c, d, e, f, u, v are coordinate transformation parameter, when calculating, choose 4 reference points and set up 8 equations, and each reference point all needing to have areal coordinate and corresponding two dimensional image coordinate two-dimensionally from described pattern identification plate.In the present embodiment, 4 reference points can be arranged in same pattern identification plate, also can be arranged in different pattern identification plate, preferably adopt in different pattern identification plate, in the embodiment that the present invention is more preferably, in each pattern identification plate, choose a reference point.
In the present embodiment, pixel filling can be adopted the pixel of the image before homogeneous coordinate transformation to be mapped one at a time in the image after getting back to homogeneous coordinate transformation and determine its gray level.If before homogeneous coordinate transformation image pixel-map to image after homogeneous coordinate transformation four pixels between, then its gray-scale value is determined by grey scale interpolation algorithm, preferred employing nearest neighbor interpolation, namely the adjoint point pixel grey scale that around capture vegetarian refreshments, four adjoint point pixel middle distances are nearest as the gray scale of this point, thus makes image truer.
After utilizing Aerial Images to generate orthograph, described realistic picture is transferred to scene photo generating apparatus, described realistic picture as a setting image shows at the display module of described scene photo generating apparatus, and the template generation module of described scene photo generating apparatus generates vehicle image and road edge image according to the vehicle of background image and road edge and the position that vehicle is corresponding with road edge described in display module shows.
In the present embodiment, the template generation module of described scene photo generating apparatus generates vehicle image and road edge image according to the vehicle of background image and road edge, the generation method of concrete vehicle image is: generate car modal in the vehicle region of background image, vehicle edge search is carried out centered by car modal position, extract edge contour, and adopt rigid transformation to carry out registration to car modal according to the edge contour extracted.In an embodiment be more preferably of the present invention, vehicle is drawn, car modal is moved to the vehicle region of background image, now Candy operator is utilized to carry out Edge Search to region centered by car modal position startup, extract edge contour, and adopt rigidity affined transformation to carry out registration to car modal according to the profile extracted.
The generation method of road edge image is: in the road edge Area generation road template of background image, described road template is straight line or curve, carry out Edge Search in road template both sides, extract edge contour, and adopt rigid transformation to carry out registration to road template according to the profile extracted.In an embodiment be more preferably of the present invention, road edge is drawn, first draw straight line or curve along edge according to standard road template, now will start with the Edge Search of curve plotting both sides certain area, extract edge contour, and adopt rigid transformation to carry out registration to road template according to the profile extracted, in the preferred implementation that the present invention is other, manual type also can be adopted first to draw straight line or curve along edge according to standard road template.In the present embodiment, for graticule and darker vehicle impression, braking print, watermark drafting also use same algorithm realization.
Above step achieves the drafting of the significant traffic element of contrast, for non-traffic elements such as environmental objects, the object that is scattered, more shallow road surface scratch and braking tracks, in the present embodiment, the environmental objects of template generation module detection background image, the object that is scattered, more shallow road surface scratch and braking track, and judge its type according to its present position and shape, such as, if in roadside, be judged as environmental objects, if on road surface and scattered distribution, be judged as the object that is scattered; If on road surface and continuously certain distance, is judged as more shallow road surface scratch and braking track, after template generation module judges type, extract the profile of border subject image, fall-out volume image, more shallow road surface scratch image and braking track, according to corresponding template generation environmental objects image, fall-out volume image, more shallow road surface scratch image and braking track image and the position that environmental objects, the object that is scattered, more shallow road surface scratch and braking track are corresponding described in display module show.In the preferred implementation that the present invention is other, the template also can called by hand in template generation module according to on-site land survey personnel is drawn, and regulates particular location and size according to background image, takes the mode of mask and background traffic element phase registration.
S4: distance labeling module is measured the distance between traffic element and marks on display module.In the present embodiment, concrete grammar is: after traffic element is completed, in a segment distance known according to the scene of the accident and background image, full figure engineer's scale is set up in the contrast of respective distance, and distance labeling module is measured the distance between traffic element and generated mark and show on display module.In present embodiment, the distance of the Distance geometry adjacent traffic element closest approach between distance labeling module mark traffic element center.
S5: on display module, other information that standard field figure needs are marked.In the present embodiment, specifically index note road direction, map orientation.In the present embodiment, the rule that road direction can be kept to the right according to vehicle in China's road is determined; Direction in map-making manually can be added by input equipment, and in the present embodiment, all contents that can not automatically generate all can manually be added.
S6: delete background image from display module, subzone generates template and generates on described display module and show subzone.In the present embodiment, subzone comprises gauge outfit region, remarks region, signature region, date region, subzone generates template and generates subzone in the display module lower right corner, and the size of subzone also can manually can regulate for the size of setting.
In this enforcement, whole scene photo product process completes, and preserves and exports as polar plot or bitmap, also can connect printer and directly realize printing in the scene of a traffic accident.
It should be noted that, the present invention is not only applicable to the scene of a traffic accident, is suitable for too scenes such as demolition site, and the on-the-spot map generalization method of concrete orthogonal projection can refer to step of the present invention and carries out, and these methods are all among protection scope of the present invention.
In the description of this instructions, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, identical embodiment or example are not necessarily referred to the schematic representation of above-mentioned term.And the specific features of description, structure, material or feature can combine in an appropriate manner in any one or more embodiment or example.
Although illustrate and describe embodiments of the invention, those having ordinary skill in the art will appreciate that: can carry out multiple change, amendment, replacement and modification to these embodiments when not departing from principle of the present invention and aim, scope of the present invention is by claim and equivalents thereof.
Claims (6)
1., based on a traffic accident scene diagram rapid generation for Aerial Images, it is characterized in that, comprise the steps:
S1: utilize platform of taking photo by plane take scene of the accident image and generate the orthograph of outdoor scene, specifically comprise the steps:
S21: construct platform of taking photo by plane;
S22: shooting scene of the accident overhead view image;
S23: geometry correction is carried out to described overhead view image;
S24: carry out homogeneous coordinate transformation to described overhead view image, by the coordinate system transformation of described overhead view image to orthogonal projection coordinate system;
S2: described orthograph is transferred to scene photo generating apparatus, described orthograph as a setting image shows at the display module of described scene photo generating apparatus, the template generation module of described scene photo generating apparatus generates vehicle image and road edge image according to the vehicle of background image and road edge and the position that vehicle is corresponding with road edge described in display module shows
The generation method of vehicle image is: generate car modal in the vehicle region of background image, vehicle edge search is carried out centered by car modal position, extract edge contour, and adopt rigid transformation to carry out registration to car modal according to the edge contour extracted;
The generation method of road edge image is: in the road edge Area generation road template of background image, described road template is straight line or curve, carry out Edge Search in road template both sides, extract edge contour, and adopt rigid transformation to carry out registration to road template according to the profile extracted;
S3: template generation module according to the environmental objects of background image, the object that is scattered, more shallow road surface scratch and braking track build environment subject image, fall-out volume image, more shallow road surface scratch image and braking track image and the position that environmental objects, the object that is scattered, more shallow road surface scratch and braking track are corresponding described in display module show;
S4: distance labeling module is measured the distance between traffic element and marks on display module, and method is:
After traffic element is completed, in a segment distance known according to the scene of the accident and background image, full figure engineer's scale is set up in the contrast of respective distance, and distance labeling module is measured the distance between traffic element and generated to be labeled on display module and shows;
S5: on display module, other information that standard field figure needs are marked;
S6: delete background image from display module, subzone generates template and generates on described display module and show subzone.
2., as claimed in claim 1 based on the traffic accident scene diagram rapid generation of Aerial Images, it is characterized in that, the step of described geometry correction is:
S31: utilize two-dimensional calibrations plate to demarcate camera, construct image mapping equation, obtain inner parameter and the external parameter of camera, described inner parameter comprises distortion factor;
S32: the numerical value of distortion factor is adjusted to 0, keeps other parameter constant, obtains the inner parameter matrix of new camera;
S33: the inner parameter utilizing camera old substitutes into image mapped equation, solve the imaging plane coordinate that distorted image pixel coordinate is corresponding, recycle described new camera internal parameter and substitute into image mapped equation, bring imaging plane coordinate surface into new image mapped equation, obtain the image pixel coordinates after correcting, then realize color reduction by gray-level interpolation.
3., as claimed in claim 2 based on the traffic accident scene diagram rapid generation of Aerial Images, it is characterized in that, the described two-dimensional calibrations plate that utilizes is demarcated camera, construct image mapping equation, and the step of the inner parameter and external parameter that obtain camera is:
S41: prepare two-dimensional calibrations plate, described two-dimensional calibrations plate has the pattern with certain area that at least 9, radiuses high with background contrasts and ranks spacing are fixed;
S42: utilize camera to be calibrated to take the image containing described scaling board of different angles;
S43: utilize image recognition algorithm search for the pattern in shooting image and locate and extract center-of-mass coordinate;
S44: utilize the two-dimentional actual coordinate of pattern and the described center-of-mass coordinate of extraction on scaling board to set up mapping equation, ask its optimum solution, obtain camera internal parameter and external parameter, described mapping equation is:
P
c＝RP
w+Τ；
Wherein, R is rotation matrix, and Τ is translation matrix, and described R, Τ are the external parameter of camera; P
wfor world coordinates, with (x
w, y
w, z
w) represent coordinate points in world coordinates, P
cfor it transforms to the coordinate in camera coordinates system, with (x
c, y
c, z
c) represent coordinate points in camera coordinates system; F is focal length, and u, v are desirable imaging plane coordinate; K is distortion factor, and u', v' are actual imaging planimetric coordinates; R is pixel line number, and c is pixel columns, S
x, S
yfor picture centre pixel coordinate, C
x, C
yfor the coordinate of principal point in imaging coordinate system.
4., as claimed in claim 1 based on the traffic accident scene diagram rapid generation of Aerial Images, it is characterized in that, the homogeneous coordinate transformation equation adopted in step S24 is:
Wherein, a, b, c, d, e, f, u, v are coordinate transformation parameter, when calculating, choose 4 reference points and set up 8 equations, and each reference point all needing to have areal coordinate and corresponding two dimensional image coordinate two-dimensionally.
5. the traffic accident scene diagram quick-speed generation system based on Aerial Images, it is characterized in that, comprise take photo by plane platform and the scene photo generating apparatus that is connected with described platform of taking photo by plane, described scene photo generating apparatus comprises display module, template generation module, distance labeling module and subzone generation module;
Described display module is connected with subzone generation module with described template generation module, distance labeling module respectively, described template generation module for generating traffic element image and non-traffic element image on described display module, described distance labeling module is for marking the distance between described traffic element, and described subzone generation module for generating subzone on display module.
6. as claimed in claim 5 based on the traffic accident scene diagram quick-speed generation system of Aerial Images, it is characterized in that, described platform of taking photo by plane comprises can go up to the air mobile device (2) and the camera (1) that carries thereof, described camera (1) shooting the scene of the accident (3) image and by described image transmitting to processor (4), described processor (4) method according to claim 1 utilizes Aerial Images to generate digitizing scene photo, obtains real accident scene.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310272101.XA CN103366555B (en) | 2013-07-01 | 2013-07-01 | Aerial image-based traffic accident scene image rapid generation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310272101.XA CN103366555B (en) | 2013-07-01 | 2013-07-01 | Aerial image-based traffic accident scene image rapid generation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103366555A CN103366555A (en) | 2013-10-23 |
| CN103366555B true CN103366555B (en) | 2015-06-17 |
Family
ID=49367800
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310272101.XA Active CN103366555B (en) | 2013-07-01 | 2013-07-01 | Aerial image-based traffic accident scene image rapid generation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103366555B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781476A (en) * | 2016-12-22 | 2017-05-31 | 中国人民解放军第三军医大学第三附属医院 | Vehicle dynamic position analysis method in traffic accident |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105550669A (en) * | 2016-01-27 | 2016-05-04 | 大连楼兰科技股份有限公司 | Intelligent accident survey method based on image identification |
| CN105700791A (en) * | 2016-03-04 | 2016-06-22 | 沈阳天择智能交通工程有限公司 | Road traffic accident field sketch recognizing and drawing method |
| CN105721751A (en) * | 2016-03-28 | 2016-06-29 | 中国人民解放军第三军医大学第三附属医院 | Method for collecting information of night traffic accident scene |
| WO2018032295A1 (en) * | 2016-08-16 | 2018-02-22 | 华为技术有限公司 | Accident scene reconstruction method and device, and moving monitoring apparatus |
| CN108389392A (en) * | 2018-04-04 | 2018-08-10 | 广东容祺智能科技有限公司 | A kind of traffic accident responsibility identification system based on machine learning |
| CN108832986B (en) * | 2018-05-20 | 2021-03-16 | 北京工业大学 | Multisource data management and control platform based on world integration |
| CN109163706A (en) * | 2018-07-17 | 2019-01-08 | 长沙市公安局交通警察支队 | Traffic accident scene diagram method for drafting and system, plotting equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100493207C (en) * | 2007-03-14 | 2009-05-27 | 北京理工大学 | Distortion measurement and correction method for CCD shooting system and comprehensive test target |
| CN102073846B (en) * | 2010-12-15 | 2013-06-05 | 同济大学 | Method for acquiring traffic information based on aerial images |
| KR20120067890A (en) * | 2010-12-16 | 2012-06-26 | 한국전자통신연구원 | Apparatus for video analysis and method thereof |
| KR101060528B1 (en) * | 2011-05-06 | 2011-08-30 | 웅진보안시스템(주) | Image processing system and operating method for security system |
| CN102436738B (en) * | 2011-09-26 | 2014-03-05 | 同济大学 | Traffic monitoring device based on unmanned aerial vehicle (UAV) |
| CN102564403B (en) * | 2012-01-06 | 2014-11-19 | 上海交通大学 | Traffic accident site rapid mapping system based on image guiding |
| CN103186892B (en) * | 2013-04-01 | 2015-11-25 | 中国人民解放军第三军医大学第三附属医院 | Aerial Images is utilized to generate the method and system of equal proportion outdoor scene scene photo |
-
2013
- 2013-07-01 CN CN201310272101.XA patent/CN103366555B/en active Active
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106781476A (en) * | 2016-12-22 | 2017-05-31 | 中国人民解放军第三军医大学第三附属医院 | Vehicle dynamic position analysis method in traffic accident |
| CN106781476B (en) * | 2016-12-22 | 2019-08-20 | 中国人民解放军第三军医大学第三附属医院 | Vehicle dynamic position analysis method in traffic accident |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103366555A (en) | 2013-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103366555B (en) | Aerial image-based traffic accident scene image rapid generation method and system | |
| CN103186892B (en) | Aerial Images is utilized to generate the method and system of equal proportion outdoor scene scene photo | |
| CN108694882B (en) | Method, device and equipment for labeling map | |
| CN111540048B (en) | Fine live-action three-dimensional modeling method based on space-ground fusion | |
| CN102472686B (en) | Driver's aid device and driver's aid system | |
| CN101319895B (en) | Hand-hold traffic accident fast on-site coordinate machine | |
| KR101445739B1 (en) | Position Detecting Method of Road Traffic Sign | |
| CN100458359C (en) | Small-displacement measuring system in long-distance plane | |
| CN109871776B (en) | All-weather lane line deviation early warning method | |
| CN103575395B (en) | A kind of outfield absolute radiation calibration method and system | |
| CN108221603A (en) | Road surface three-dimensional information detection device, the method and system of a kind of road | |
| CN105551039A (en) | Calibration method and calibration device for structured light 3D scanning system | |
| CN106093963A (en) | A kind of method improving railway vehicle-mounted Laser Radar Scanning data precision | |
| JP2012511697A (en) | How to generate a geodetic reference database | |
| CN104034305B (en) | A kind of monocular vision is the method for location in real time | |
| CN106978774A (en) | A kind of road surface pit automatic testing method | |
| CN103954458A (en) | Non-contacting type four-wheel aligner and detecting method thereof | |
| CN106960591A (en) | A kind of vehicle high-precision positioner and method based on road surface fingerprint | |
| CN104120645A (en) | Automatic test data positioning system and method for pavement condition | |
| CN106705962A (en) | Method and system for acquiring navigation data | |
| US20180350085A1 (en) | Method and apparatus for homography estimation | |
| Su et al. | Developing an unmanned aerial vehicle-based rapid mapping system for traffic accident investigation | |
| CN104732870B (en) | Make the measuring method and system of large-scale map | |
| CN109920009A (en) | Control point detection and management method and device based on two dimensional code mark | |
| Liu et al. | Accurate mapping method for UAV photogrammetry without ground control points in the map projection frame |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |